A method for predicting oil flow rates is provided. The method includes accessing historical data from a plurality of databases, accessing historical perforation data and historical reservoir properties data from a simulation model, and determining fluid flow values and rock quality index values associated with perforated intervals of the plurality of wells. The method further includes corresponding the fluid flow values and rock quality values to the well production data, training, using the plurality of input values, a machine learning model for predicting oil flow values at perforated intervals of a plurality of target wells, predicting, using the trained machine learning model, the oil flow values at the perforated intervals of the plurality of target wells, and generating a synthetic production log that includes the predicted oil flow values at the perforated intervals of the plurality of target wells.
Legal claims defining the scope of protection, as filed with the USPTO.
2. The method of claim 1, wherein the simulation model corresponds to a reservoir simulation model.
3. The method of claim 1, wherein the historical reservoir properties data are associated with one or more of porosity values, permeability values, well geometry, rock classifications, and stratigraphic zone values.
4. The method of claim 1, wherein the perforated intervals of the plurality of wells and an additional plurality of wells are associated with a plurality of depth values such that each perforated interval is associated with a depth value of the plurality of depth values.
5. The method of claim 1, wherein the machine learning model is trained on one or more of a GBM algorithm, a random forest algorithm, a tree ensemble algorithm, and XGBoost algorithm.
7. The method of claim 6, further comprising determining contribution fraction values for additional perforated intervals of each of the additional plurality of wells.
9. The method of claim 8, further comprising dividing the interval flow value of each of the additional perforated intervals of each of the additional plurality of wells by the total flow value of each well that corresponds to each perforated interval.
11. The non-transitory computer-readable medium of claim 10, wherein the simulation model corresponds to a reservoir simulation model.
12. The non-transitory computer-readable medium of claim 10, wherein the historical reservoir properties data are associated with one or more of porosity values, permeability values, well geometry, rock classifications, and stratigraphic zone values.
13. The non-transitory computer-readable medium of claim 10, wherein the perforated intervals are associated with a plurality of depth values such that each perforated interval is associated with a depth value of the plurality of depth values.
14. The non-transitory computer-readable medium of claim 10, wherein the machine learning model is trained on one or more of a GBM algorithm, a random forest algorithm, a tree ensemble algorithm, and XGBoost algorithm.
16. The non-transitory computer-readable medium of claim 15, wherein the stored instructions, when executed by the one or more processors of the computing device, further cause the computing device to determine contribution fraction values for additional perforated intervals of each of the additional plurality of wells.
18. The non-transitory computer-readable medium of claim 17, wherein the stored instructions, when executed by the one or more processors of the computing device, further cause the computing device to divide the interval flow value of each of the additional perforated intervals of each of the additional plurality of wells by the total flow value of each well that corresponds to each perforated interval.
20. The method of claim 19, further comprising generating a synthetic production log that includes the oil flow values at the perforated intervals of the plurality of target wells.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
January 28, 2021
April 9, 2024
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.